Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/bacchus-labs/wrangler/validate-session-adherencegit clone --depth 1 https://github.com/bacchus-labs/wranglerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/bacchus-labs/wrangler/validate-session-adherence)<a href="https://agentmods.dev/commands/bacchus-labs/wrangler/validate-session-adherence"><img src="https://agentmods.dev/badge/commands/bacchus-labs/wrangler/validate-session-adherence.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.06286 |
| Opus 5 | $0.00017 | $0.03143 |
| Sonnet 5 | $0.00007 | $0.01257 |
| Haiku 4.5 | $0.00003 | $0.00629 |
Grade A, and why
validate-session-adherence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 933 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are conducting a compliance audit of the AI agent's adherence to wrangler workflows and skill guidelines during this session.
Purpose: Trust but verify - validate that wrangler's systematic processes were actually followed.
This is NOT gap analysis (that's /wrangler:analyze-session-gaps). This is compliance auditing: Did we follow the processes we said we would?
Input
User suspicion (optional): "{user's specific concern or focus area}"
If user provided suspicion, focus analysis there while still covering all areas.
Your Task
Phase 1: Conversation Analysis (Scope and Context)
Analyze last 30-50 messages to understand what work was done:
-
Identify Tasks Performed:
- Feature implementations
- Bug fixes
- Refactoring
- Code reviews
- Planning activities
- Documentation work
- Testing activities
-
Extract Key Events:
- File modifications (code, tests, specs)
- Completion claims ("done", "ready", "works")
- Skill announcements (🔧 Using Skill: ...)
- Test executions
- Build commands
- Commit operations
- Subagent dispatches
-
Build Timeline:
Message #N: User requested feature X Message #N+2: Agent modified file.ts Message #N+5: Agent claimed "tests pass" Message #N+7: Agent committed changes -
Note User Feedback:
- Corrections requested
- Concerns raised
- Questions asked
- Skepticism expressed
Phase 2: Skill Invocation Compliance
Reference: docs/skill-invocation-patterns.md
For each task identified, determine:
2.1 Expected Skills
Based on task pattern, which skills SHOULD have been invoked?
Use skill-invocation-patterns.md mappings:
- Feature implementation →
check-constitutional-alignment,test-driven-development,requesting-code-review,verification-before-completion - Bug fix →
systematic-debugging,test-driven-development,requesting-code-review,verification-before-completion - Code changes →
test-driven-development(ALWAYS),requesting-code-review(ALWAYS except 3 exceptions) - Multiple failures →
dispatching-parallel-agents(if 3+ independent) - Complex implementation →
writing-plans
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 933 lines · 34 tokens per session scan A 4823675593ae
validate-session-adherence is a command published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 6,286 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.